Skip to main content
SpringerLink
Log in

Meaning and Uncertainty Inherent in Understanding Images, Spatial-Taxon Hierarchy, Word Annotation and Relevant Context

  • Conference paper
  • First Online:
Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications (IPMU 2018)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 855))

  • 1240 Accesses

Abstract

This paper explores the meaning and uncertainty inherent in (a) understanding image hierarchies; (b) describing them with words; and (c) navigating the abstraction context of the viewer. A spatial-taxon hierarchy, a standardized scene architecture, partitions an image into a foreground, subject and salient objects and/or sub-objects. The introduction starts with a thought experiment (Thought experiments, borrowed from the model-theoretic isomorphism standard of structure-mapping theory, enable readers to compare two systems thought to be similar. It’s a form of inductive reasoning that expands knowledge in the face of uncertainty (Holland et al. 1986 [13]) by providing an explicit representation of how two systems are similar. Though the conclusion that the two systems do share an isomorphic structure can only be supported via various degrees of truth (fuzzy membership), it establishes its plausibility. Analogical reasoning is natural to human thought and communication making it useful for scientific papers.) based on a poem & an image landscape. The thought experiment is intended to provide analogical inference as scaffolding for the rest of the paper. The results of experimental data of human annotated spatial-taxon and corresponding word descriptions of two images are presented. The experimental results are analyzed in terms of spatial-taxon designation and the meaning & uncertainty presented by the human annotations. The results support the fuzzy spatial-taxon hierarchy of human scene perception described by other works, show that word descriptions depend on spatial-taxon designation and that long tail word distributions require unbounded possibility with semantic uncertainty (type 2 fuzzy sets) for the word counts in the probability distribution. Deep learning image recognition, Zadeh information restriction principal, Shannon’s distinction between information content and semantics, customized image descriptions and fuzzy inference techniques are explored.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    I chose the term “other mind” used in cognitive psychology, after personal communication with Professor Zadeh regarding an example of unprecisiated restriction, which he described as “a perception evoked in one’s mind.” In this paper “other-mind uncertainty” refers to the unknown differences between each human’s individual mental construct. It does not refer to uncertainty in the word semantics, context or particular definitions.

  2. 2.

    Excluding Quantum Mechanics.

  3. 3.

    I could have used subset (\(ST_1\) - \(ST_2\)) as a root for a new child subset. However, to make this readable, I limit the definition to spatial-taxon children stemming from a single initial image root.

  4. 4.

    Since deep learning neural nets learn only possible classification within bound of composite training data, they are also limited by statistics.

  5. 5.

    An ensemble, often referred to as an alphabet, is the set of possible outcomes of word annotations and pixel designations. In this paper, allowed pixel designations are spatial-taxons or the edges that outline spatial-taxons. The word annotations collected and shown in the results are outcomes. Note that since nested spatial-taxons are not mutually exclusive, the results count word annotations for each child spatial-taxon [5], which by the definition of spatial-taxons are included in both the parent taxon and child taxons [8, 9].

References

  1. Barghout, L., Lee, L.: Perceptual information processing system. USPTO patent application number: 20040059754 (2003)

    Google Scholar 

  2. Barghout, L.: System and Method for Edge Detection in Image Processing and Recognition. WIPO Patent Application. WO/2007/044828 (2006)

    Google Scholar 

  3. Barghout, L.: Linguistic Image Label Incorporating Decision Relevant Perceptual, Semantic, and Relationships Data. USPTO Patent Application 20080015843 (2007)

    Google Scholar 

  4. Barghout, L.: Empirical data on the configural architecture of human scene perception using natural images. J. Vis. 9(8), 964 (2009). https://doi.org/10.1167/9.8.964

    Article  Google Scholar 

  5. Barghout, L., Winter, H., Riegel, Y.: Empirical data on the configural architecture of human scene perception and linguistic labels using natural images and ambiguous figures. J. Vis. 11, 1077 (2011)

    Article  Google Scholar 

  6. Barghout, L., Sheynin, J.: Real-world scene perception and perceptual organization: lessons from computer vision. J. Vis. 13(9), 709 (2013)

    Article  Google Scholar 

  7. Barghout, L.: Image segmentation using fuzzy spatial-taxon cut: comparison of two different stage one perception based input models of color (Bayesian Classifier and Fuzzy Constraint). Electron. Imaging 2016(16), 1–6 (2016)

    Article  Google Scholar 

  8. Barghout, L.: Visual taxometric approach to image segmentation using fuzzy-spatial taxon cut yields contextually relevant regions. In: Laurent, A., Strauss, O., Bouchon-Meunier, B., Yager, R.R. (eds.) IPMU 2014. CCIS, vol. 443, pp. 163–173. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-08855-6_17

    Chapter  Google Scholar 

  9. Barghout, L.: Spatial-taxon information granules as used in iterative fuzzy-decision-making for image segmentation. In: Pedrycz, W., Chen, S.-M. (eds.) Granular Computing and Decision-Making: Interactive and Iterative Approaches. SBD, vol. 10, pp. 285–318. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16829-6_12

    Chapter  Google Scholar 

  10. Barghout, L.: Image Segmentation Using Fuzzy-Spatial Taxon Cut (2015). https://docs.lib.purdue.edu/modvis/2015/session05/6/

  11. Barghout, L.: Using the 5th dimensions of human visual perception to inspire automated edge and texture segmentation: a fuzzy spatial-taxon approach. In: 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing (ICCI*CC). IEEE (2016)

    Google Scholar 

  12. Berger, J.: Ways of Seeing - Based on the BBC Television Series with John Berger. Transcribed by Pelican Books, p. 31 (1985)

    Google Scholar 

  13. Cancho, R.F., Sole, R.V.: Zipf ’s law and random texts. Adv. Complex Syst. 5(1), 1–6 (2002)

    Article  Google Scholar 

  14. Deng, Y., Manjunath, B., Shin, H.: Color image segmentation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2 (1999)

    Google Scholar 

  15. Fiorini, R.A.: Deep learning and deep thinking: new application framework by CICT. In: 2016 IEEE 15th International Conference on Cognitive Informatics and Cognitive Computing (ICCI*CC), pp. 117–128 (2016)

    Google Scholar 

  16. Hawkins, J., Blakeslee, S.: On Intelligence: How a New Understanding of the Brain Will Lead to the Creation of Truly Intelligent Machines. Macmillan, New York (2007)

    Google Scholar 

  17. James, W.: Principles of Psychology, 403 p. Holt, New York (1890)

    Google Scholar 

  18. Jolicoeur, P., Gluck, M.A., Kosslyn, S.M.: Pictures and names: making the connection. Cogn. Psychol. 16, 243–275 (1984)

    Article  Google Scholar 

  19. Klein, S.A.: Will robots see? In: Spatial Vision in Humans and Robots: The Proceedings of the 1991 York Conference on Spatial Vision in Humans and Robots. Cambridge University Press (1993)

    Google Scholar 

  20. Marcus, G.: Deep learning: a critical appraisal. arXiv preprint arXiv:1801.00631 (2018)

  21. Miyajima, K., Ralescu, A.: Spatial organization in 2D segmented images: representation and recognition of primitive spatial relations. Fuzzy Sets Syst. 65(2-3), 225–23 (1994)

    Article  Google Scholar 

  22. Nelson, R., Palmer, S.E.: Of holes and wholes: the perception of surrounded regions. Perception 30(10), 1213–1226 (2001)

    Article  Google Scholar 

  23. O’Regan, K.: Experience is not something we feel but something we do: a principled way of explaining sensory phenomenology, with Change Blindness and other empirical consequences. Talk given at Bressanone on 24 January 2001. Source for Ghost-woman image

    Google Scholar 

  24. Palmer, S.: Vision Science: Photons to Phenomenology, MIT Press, Cambridge (1999)

    Google Scholar 

  25. Rosch, E.H.: Cognitive representation of semantic categories. J. Exp. Psychol. 104(3), 192–233 (1975)

    Article  Google Scholar 

  26. Rosch, E.H., Mervis, C.B., Gray, W.D., Johnson, D.M., Boyes-Braem, P.: Basic objects in natural categories. Cogn. Psychol. 8(3), 382–439 (1976)

    Article  Google Scholar 

  27. Ruscio, J., Haslam, N., Ruscio, A.: Introduction to Taxometric Method. Lawrence Erlbaum Associates, Mahwah (2006)

    Google Scholar 

  28. Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 623–656 (1948)

    Article  MathSciNet  Google Scholar 

  29. Simon, H.: The architecture of complexity. Proc. Am. Philos. Soc. 106(6), 467–482 (1962)

    Google Scholar 

  30. Tononi, G., Boly, M., Massimini, M., Koch, C.: Integrated information theory: from consciousness to its physical substrate. Nat. Rev. Neurosci. 17(7), 450–461 (2016)

    Article  Google Scholar 

  31. Treisman, A.M.: Strategies and models of selective attention. Psychol. Rev. 76(3), 282–299 (1969)

    Article  Google Scholar 

  32. Wertheimer, M.: Laws of Organization in Perceptual Forms (partial translation) A Sourcebook of Gestalt Psychology. In: Ellis, W.B. (ed.), pp. 71–88, Harcourt Brace (1938)

    Google Scholar 

  33. Zadeh, L.: Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trans. Syst. Man Cybern. 1, 28–44 (1973)

    Article  MathSciNet  Google Scholar 

  34. Zadeh, L.A.: Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst. 90, 111–127 (1997)

    Article  MathSciNet  Google Scholar 

  35. Zadeh, L.: Generalized theory of uncertainty (GTU): principal concepts and ideas. Comput. Stat. Data Anal. 51, 15–26 (2006)

    Article  MathSciNet  Google Scholar 

  36. Zadeh, L.: Toward a restriction-centered theory of truth and meaning (RCT). Inf. Sci. 248, 1–14 (2013)

    Article  MathSciNet  Google Scholar 

  37. Zipf, G.K.: Human Behavior and the Principle of Least Effort: An introduction to human Ecology. Addison-Wesley, Cambridge (1972)

    Google Scholar 

Download references

Acknowledgments

I thank Dr. Lotfi Zadeh for mentoring me on my graduate work at U.C. Berkeley and for inviting as a visiting scholar in the Electrical Engineering and Computer Science Department at University of California at Berkeley (2014 2017) to work on my upcoming book on Fuzzy, Bayesian, Hybrid methods for Computer Vision. I thank my collaborators Haley Winter, Analucia DaSivla, Yurik Riegal, Colin Rhodes, Eric Rabinowitz and Shawn Silverman. I thank Ralph Schmidt-Dunker for help with editing. BurningEyeDeas LLC, an organization that does research at the Burningman Art Festival. Data posted at www.burningeyedeas.com and/or laurenbargout.com.

Author information

Authors and Affiliations

  1. Berkeley Institute for Soft Computing (BISC), Visiting Scholar 2014 - 2017, U.C. Berkeley Electrical Engineering and Computer Sciences, Berkeley, CA, USA

    Lauren Barghout

Authors
  1. Lauren Barghout
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lauren Barghout .

Editor information

Editors and Affiliations

  1. Universidad de Cádiz, Cádiz, Cadiz, Spain

    Jesús Medina

  2. Universidad de Málaga, Málaga, Málaga, Spain

    Manuel Ojeda-Aciego

  3. Universidad de Granada, Granada, Spain

    José Luis Verdegay

  4. Institute for Research and Applications, University of Ostrava, Ostrava, Czech Republic

    Irina Perfilieva

  5. LIP6, Université Pierre et Marie Curie, CNRS, Paris, France

    Bernadette Bouchon-Meunier

  6. Iona College, New Rochelle, New York, USA

    Ronald R. Yager

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG, part of Springer Nature

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Barghout, L. (2018). Meaning and Uncertainty Inherent in Understanding Images, Spatial-Taxon Hierarchy, Word Annotation and Relevant Context. In: Medina, J., Ojeda-Aciego, M., Verdegay, J., Perfilieva, I., Bouchon-Meunier, B., Yager, R. (eds) Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications. IPMU 2018. Communications in Computer and Information Science, vol 855. Springer, Cham. https://doi.org/10.1007/978-3-319-91479-4_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-91479-4_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-91478-7

  • Online ISBN: 978-3-319-91479-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation